vinothchandar commented on a change in pull request #3865:
URL: https://github.com/apache/hudi/pull/3865#discussion_r757098143
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/log/LogReaderUtils.java
##########
@@ -62,23 +65,23 @@ private static Schema
readSchemaFromLogFileInReverse(FileSystem fs, HoodieActive
return writerSchema;
}
- public static Schema readLatestSchemaFromLogFiles(String basePath,
List<String> deltaFilePaths, Configuration config)
+ public static Schema readLatestSchemaFromLogFiles(String basePath,
List<Pair<String, Long>> logFilePathSizePairs, Configuration config)
Review comment:
should we jsut pass the `LogFile` object as is without having to deal
with Pair?
##########
File path:
hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/realtime/RealtimeBootstrapBaseFileSplit.java
##########
@@ -19,21 +19,25 @@
package org.apache.hudi.hadoop.realtime;
import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
import org.apache.hudi.hadoop.BootstrapBaseFileSplit;
import org.apache.hadoop.mapred.FileSplit;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
+import java.util.ArrayList;
import java.util.List;
+import java.util.stream.Collectors;
/**
* Realtime File Split with external base file.
*/
public class RealtimeBootstrapBaseFileSplit extends BootstrapBaseFileSplit
implements RealtimeSplit {
private List<String> deltaLogPaths;
Review comment:
do we need this though, now?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
